{"id":15235418,"url":"https://github.com/replicate/flux-fine-tuner","last_synced_at":"2025-04-08T10:33:08.704Z","repository":{"id":257804469,"uuid":"842650695","full_name":"replicate/flux-fine-tuner","owner":"replicate","description":"Cog wrapper for ostris/ai-toolkit + post-finetuning cog inference for flux models","archived":false,"fork":false,"pushed_at":"2025-03-31T10:21:33.000Z","size":1710,"stargazers_count":375,"open_issues_count":13,"forks_count":60,"subscribers_count":12,"default_branch":"main","last_synced_at":"2025-04-01T09:33:47.319Z","etag":null,"topics":["flux"],"latest_commit_sha":null,"homepage":"https://replicate.com/ostris/flux-dev-lora-trainer/train","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/replicate.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2024-08-14T19:28:49.000Z","updated_at":"2025-03-31T11:32:41.000Z","dependencies_parsed_at":"2024-12-16T06:01:50.242Z","dependency_job_id":"760b10ed-9e2e-47b8-9bb9-247bf0b2ded9","html_url":"https://github.com/replicate/flux-fine-tuner","commit_stats":{"total_commits":134,"total_committers":11,"mean_commits":"12.181818181818182","dds":0.6119402985074627,"last_synced_commit":"0bf7bb136dda78786cdeb12d572b6b831e6951fd"},"previous_names":["replicate/flux-fine-tuner"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/replicate%2Fflux-fine-tuner","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/replicate%2Fflux-fine-tuner/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/replicate%2Fflux-fine-tuner/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/replicate%2Fflux-fine-tuner/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/replicate","download_url":"https://codeload.github.com/replicate/flux-fine-tuner/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247824006,"owners_count":21002185,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["flux"],"created_at":"2024-09-29T08:01:41.933Z","updated_at":"2025-04-08T10:33:08.654Z","avatar_url":"https://github.com/replicate.png","language":"Python","funding_links":[],"categories":["Python"],"sub_categories":[],"readme":"# flux-fine-tuner\n\nThis is a [Cog](https://cog.run) training model that creates LoRA-based fine-tunes for the [FLUX.1](https://replicate.com/blog/flux-state-of-the-art-image-generation) family of image generation models.\n\nIt's live at [replicate.com/ostris/flux-dev-lora-trainer](https://replicate.com/ostris/flux-dev-lora-trainer).\n\nIt also includes code for running inference with a fine-tuned model.\n\n## Features\n\n- Automatic image captioning during training\n- Image generation using the LoRA (inference)\n- Optionally uploads fine-tuned weights to Hugging Face after training\n- Automated test suite with [cog-safe-push](https://github.com/replicate/cog-safe-push) for continuous deployment\n- Weights and biases integration\n\n## Getting Started\n\nIf you're looking to create your own fine-tuned model on Replicate, you don't need to do anything with this codebase.\n\nCheck out these guides to get started:\n\n👉 [Fine-tune Flux to create images of yourself](https://replicate.com/blog/fine-tune-flux-with-faces)\n\n👉 [Fine-tune Flux with an API](https://replicate.com/blog/fine-tune-flux-with-an-api)\n\n## Contributing\n\nIf you're here to help improve [the trainer that Replicate uses to fine-tune Flux models](https://replicate.com/ostris/flux-dev-lora-trainer), you've come to the right place.\n\nCheck out the [contributing guide](CONTRIBUTING.md) to get started.\n\n## Credits\n\nThis project is based on the [ai-toolkit](https://github.com/ostris/ai-toolkit) project, which was created by [@ostris](https://github.com/ostris). ❤️\n\n## License\n\nThe code in this repository is licensed under the [Apache-2.0 License](LICENSE).\n\nThe [ai-toolkit](https://github.com/ostris/ai-toolkit) project is licensed under the [MIT License](https://github.com/ostris/ai-toolkit/blob/main/LICENSE).\n\nFlux Dev falls under the [`FLUX.1 [dev]` Non-Commercial License](https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md).\n\n`FLUX.1 [dev]` fine-tuned weights and their outputs are non-commercial by default, but can be used commercially when running on Replicate.\n\nFlux Schnell falls under the [Apache-2.0 License](https://huggingface.co/datasets/choosealicense/licenses/blob/main/markdown/apache-2.0.md).\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Freplicate%2Fflux-fine-tuner","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Freplicate%2Fflux-fine-tuner","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Freplicate%2Fflux-fine-tuner/lists"}